Newest papers

Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks

Erik Stolt, Sanja Karilanova, Ayca Ozcelikkale · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28495 · open-access PDF

Portuguese

Os modelos Deep State-Space (Deep SSMs) mostraram promissores benefícios de desempenho e computação no processamento de dados de séries de tempo com dependências temporais complexas. As redes neurais de pico (SNNs) constituem uma classe de SSMs profundos inspirados biologicamente, onde os blocos de computação se comunicam através de picos, eventos discretos de bits únicos em vez de funções de ativação contínua. Uma tarefa particularmente importante no processamento de séries de tempo é a previsão, ou seja, a previsão de valores futuros de uma seqüência a partir de observações passadas sozinhas.

Machine translation (Meta M2M100); the English original follows.

Abstract

Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spiking neural networks (SNNs) constitute a biologically inspired class of deep SSMs, where computing blocks communicate through spikes, discrete single-bit events rather than continuous activation functions. A particularly important task in time-series processing is forecasting, i.e. predicting future values of a sequence from past observations alone. However, how to best perform forecasting with SNNs is an open question, where t

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange